① 他说过的话

14 条

你给一枚没有转向或制导的火箭加火箭燃料，它就只会转圈直到爆炸
you add rocket you know, rocket fuel to a rocket that has no steering or guidance and just go in circles until it blows up
—— Liz Fong-Jones · [09:34]

指向原始笔记的链接

AI 会复制你代码库中已有的模式。如果你有五种不同的做事方式，AI 会变得非常困惑，然后创造出第六种、第七种做事方式。
AI copies existing patterns that exist in your code base. If you have five different ways of doing something, AI will become very confused and it will create six ways or seven ways in ways of doing it.
—— Liz Fong-Jones · [11:13]

指向原始笔记的链接

因为机器永远不会感到无聊，让它们给你的代码库添加遥测是一件很棒的事情
because the machines never get bored, it’s a great thing to do to have them add telemetry to your code base
—— Liz Fong-Jones · [13:24]

指向原始笔记的链接

Autobot 每天大概只产出这些拉取请求中的五个。所以它并不是拉取请求的主要创作者，它是这些拉取请求 100% 的审查者
the Autobot is producing maybe five of those pull requests per day. So it’s not the majority creator of the pull requests, it is the 100% reviewer of those pull requests
—— Liz Fong-Jones · [14:34]

指向原始笔记的链接

任何真正的生产系统恐怕都不应该是一个黑暗工厂，至少在目前这个阶段是如此
any real production system should probably not be a dark factory, at least at this time
—— Liz Fong-Jones · [15:46]

指向原始笔记的链接

你的车里有了自适应巡航控制，并不意味着你可以完全放开方向盘
just because you have adaptive cruise control in your car doesn’t mean that you can fully let go of the wheel
—— Liz Fong-Jones · [16:11]

指向原始笔记的链接

我们发布的 pull request 翻了一倍，而我们看到的事故是原来的 1.5 倍
we were shipping twice as many pull requests and we are seeing you know 1.5 times as many incidents
—— Liz Fong-Jones · [23:24]

指向原始笔记的链接

我们应该对齐的是方向是否正确，而不是这个实现是否完全正确
that’s the thing that we should be aligning on is is the direction correct and not, you know, is this implementation exactly correct
—— Liz Fong-Jones · [24:46]

指向原始笔记的链接

如果你没有这些东西，你的智能体就只是在猜测、往飞镖盘上乱扔飞镖，它们造成的混乱可能比它们实际解决的还多
If you don’t have those things, your agents are just guessing and throwing darts at the dartboard, and they might cause more chaos than they actually solve.
—— Liz Fong-Jones · [28:55]

指向原始笔记的链接

我们正在意识到无法规模化扩展的主要事情，就是让人类去点「是」
the main thing that we are realizing does not scale is having humans click yes
—— Liz Fong-Jones · [32:21]

指向原始笔记的链接

我认为错误在于过度信任自己在时间压力和压力下做决策的能力
I think the mistake is overtrusting your ability to make decisions under time pressure and stress
—— Liz Fong-Jones · [33:14]

指向原始笔记的链接

那你为什么要信任别人的智能体呢？检查别人的工作，可能和自己动手做一样费工夫
why should you trust someone else’s agent where it might be just as much work to check the work over as if you had done it yourself?
—— Liz Fong-Jones · [40:20]

指向原始笔记的链接

你是在用 slop 对抗 slop,对吧？
You’re using slop to fight slop, right?
—— Liz Fong-Jones · [41:16]

指向原始笔记的链接

仅仅因为你能做某件事、能给别人发一个一万行的 pull request,并不意味着你应该这么做
Just because you can do something and send someone a 10,000 line pull request does not mean you should.
—— Liz Fong-Jones · [43:42]

指向原始笔记的链接

② 出现在这些集

1 集

• 《AI 写代码翻倍之后：Honeycomb 的审查、信任与主人翁意识》 — 作为联合主持

③ 他谈到的

点进去有真内容 —— 本页主要出口

Simon Maple · Honeycomb · Google · Shopify · Autobot · Anthropic · Claude · 代码审查 · 股权占比 · 可观测性

④ 也在聊「AI 编程」的人